Tool in benchmark · Version 1

Reducto in Converting a complex PDF into clean Markdown with a hosted API

Scenario-level performance from current published Results.

5 scenarios with published Results · 12 scenarios in the benchmark

How Reducto performed

Open a capability to explore its scenarios. Each row reports the test set in its published Result; counts are not combined into an overall score.

Code Extraction1 scenario · 1 with published Results
ScenarioPublished outcomesTest coverageResult
A document containing a code block
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

Reducto did not preserve the code block as fenced or preformatted Markdown. The returned file had no fences or indented code lines, while the source block’s line breaks remained and the output also altered code tokens, including `window = reload_window(reset_at, margin_minutes=45)` becoming `window reload_window (reset_at, margin_minutes=45)`.

1/1 assessed1/1 gradablePublished test setView Result →
Equations & Mathematical Notation1 scenario · 1 with published Results
ScenarioPublished outcomesTest coverageResult
A document containing mathematical equations
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

Reducto failed a document with mathematical equations: the returned Markdown contained no math markup and no fallback, and the equations were flattened into prose with missing symbols and substituted characters. This is the case: the source page shows set mathematics, while the output preserves only garbled lines instead of LaTeX, MathML, or an explicit fallback.

1/1 assessed1/1 gradablePublished test setView Result →
Heading & Section Structure2 scenarios · 1 with published Results
ScenarioPublished outcomesTest coverageResult
A document with styled headings and subheadings
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

Reducto flattened the heading structure in the Markdown output. The file contains one "#", 26 "##" headings, and no deeper levels; the document title is plain paragraph text. The two visible parent/child pairs were emitted as peers, so the nesting expected for styled headings and subheadings was not preserved.

1/1 assessed1/1 gradablePublished test setView Result →
Footnotes at the bottom of the pageNo published result
Scanned Document OCR2 scenarios · 2 with published Results
ScenarioPublished outcomesTest coverageResult
A cleanly scanned document
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Reducto accurately recovered the visible text from a cleanly scanned document. The scan’s text matched the output field by field, with the handwritten signature left as a <signature> placeholder and only two middle-dot separators dropped from the letterhead and footer lines.

1/1 assessed1/1 gradablePublished test setView Result →
A document mixing digital and scanned pages
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

The mixed PDF’s scanned page was processed rather than skipped. Reducto’s Markdown includes the image-only page 2 with its headers, table, certificate section, and recipient details, matching the digital pages’ presentation in the checked evidence.

1/1 assessed1/1 gradablePublished test setView Result →
Figures & Charts2 scenarios · 0 with published Results
ScenarioPublished outcomesTest coverageResult
A document with a data chartNo published result
A document with figures and captionsNo published result
Reading Order & Layout1 scenario · 0 with published Results
ScenarioPublished outcomesTest coverageResult
A page laid out in multiple columnsNo published result
Table Extraction2 scenarios · 0 with published Results
ScenarioPublished outcomesTest coverageResult
A simple, clearly formatted tableNo published result
A table that continues across a page breakNo published result
Text Fidelity1 scenario · 0 with published Results
ScenarioPublished outcomesTest coverageResult
An ordinary digital text documentNo published result

Reading these Results

Published evidence and test coverage answer different questions.

Publication availability

Which scenarios have a Result?

A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.

Test coverage

What does each Result cover?

Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.

Scenario scope

Inventory is not testing progress

The 12 scenarios describe this benchmark’s scope. They are not an assumed applicability or test-coverage denominator for Reducto.

Reducto in Converting a complex PDF into clean Markdown with a hosted API | AI Demos